把 JSON 数据写成 Excel 工作簿（.xlsx），落文件中转站返下载 URL（上限 20 万单元格）。
补上「只能读不能写」的缺口：AI 算完的结果一步落成正式 Excel 交付。失败自动退款。
| Name | Required | Description | Default |
|---|---|---|---|
| rows | Yes | 数据行：对象列表 [{列:值},...]，或行数组 [[v1,v2],...]（需配 columns） | |
| columns | No | 列名（rows 为行数组时必填；对象列表时忽略） | |
| filename | No | 输出文件名（可选，自动补 .xlsx） | |
| sheet_name | No | 工作表名 | Sheet1 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description mentions the limit of 200k cells and auto-refund on failure, adding behavioral context. However, lacks details on file overwrite behavior, permissions, or rate limits, which would be valuable for a write operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences plus one bullet, front-loaded with core purpose. Every sentence provides unique information: function (first sentence), context/limit (highlighted), and parameter notes. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description states it returns a download URL. Covers key constraints (cell limit, auto-refund) but omits details on error states, file size, or concurrent usage. For a tool with 4 parameters, it's adequate but not fully comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage. Description adds value by explaining the dual format for rows (object list vs. array), that columns are required for arrays, and that filename auto-appends .xlsx. These details clarify usage beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states '把 JSON 数据写成 Excel 工作簿' (write JSON data to Excel workbook), specifying the resource (.xlsx), action (write), and delivery mechanism (return download URL). Differs from siblings (inspect, query, chart) as the only write tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly addresses the gap of '只能读不能写' (only read, not write), guiding agents to use when needing to output data as Excel. Doesn't specify when not to use, but context implies alternatives are read/analysis tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
每个工具都有清晰且独特的用途：inspect查看结构，query查询数据，to_chart生成图表，write写入Excel。描述中明确区分了它们，没有重叠或混淆的可能。
命名统一使用'excel_'前缀，后接动词形式（inspect, query, write），但to_chart使用了介词结构，略微打破一致模式。整体仍可预测且清晰。
4个工具覆盖了Excel可视化的核心流程：结构查看、数据查询、图表生成、结果写入。数量适中，没有冗余，但可能缺少合并或格式调整等辅助功能。
工具集提供了从探索到输出完整闭环：先inspect了解结构，再用query获取数据，然后用to_chart生成图表，最后用write保存结果。没有明显遗漏，完全满足可视化目标。